Apnea Events Research Articles

High arousal threshold is associated with metabolic syndrome in patients with obstructive sleep apnea

ObjectiveObstructive sleep apnea (OSA) is associated with metabolic syndrome (MetS). OSA patients with high arousal threshold (ArTH) are less easy to arouse, which leads to more severe hypoxic events. We explored the relationship between high ArTH and MetS in patients with OSA. MethodsWe conducted a cross-sectional study of 112 patients with OSA (mean age 43.50 ± 11.64 years, 89.29 % male). High ArTH was based on an overnight polysomnography, and defined as none or one of the following conditions: apnea-hypopnea index (AHI) < 30 events/hour, minimum oxygen saturation > 82.5 %, or frequency of hypopnea events > 58.3 %. Metabolic syndrome and its components were defined according to the new International Diabetes Federation definition. ResultsAmong the 112 OSA patients, 51 (45.54 %) had MetS and 68 (60.71 %) had high ArTH. Logistic regression, after adjusting for confounders, showed that patients with high ArTH had higher odds for MetS (OR = 4.31, 95 % CI = 1.63–11.42, p = 0.003), central obesity (OR = 5.78, 95 % CI = 1.95–17.16, p = 0.002) and hypertriglyceridemia (OR = 2.84, 95 % CI = 1.11–7.28, p = 0.030) compared to patients with low ArTH. Furthermore, higher ArTH levels were associated with higher values for waist circumference (p-for-trend < 0.001), triglycerides (p-for-trend = 0.042), and systolic blood pressure (p-for-trend = 0.037). Moreover, patients with high ArTH had more apnea events and less hypopnea events. ConclusionsHigh ArTH is associated with MetS in OSA patients. High ArTH is a marker of the severity of cardiometabolic comorbidity in OSA.

Ictal and Postictal Central Apnea in DEPDC5-Related Epilepsy.

DEPDC5-related epilepsy carries an increased risk of sudden unexpected death in epilepsy. We evaluated the occurrence and features of ictal central apnea (ICA) in patients with pathogenic sequence variant in DEPDC5. We reviewed data of 108 patients collected in 2 independent cohorts of patients with focal epilepsy who prospectively underwent long-term video-EEG monitoring (LTVM) with cardiorespiratory polygraphy. All patients underwent (1) at least an overnight polysomnography, (2) a high-field (3T) brain MRI study, and (3) CSF analysis when clinically indicated. Genetic testing (next-generation sequencing [NGS]) was offered for diagnostic purposes to patients with focal epilepsy of unknown etiology. In this cohort, NGS was finally performed in 29 patients, resulting in DEPDC5 pathogenic mutations in 5 patients. According to the presence of ictal apnea events, 5 of 14 patients with ICA showed pathogenic DEPDC5 variants (35%) while none of the 15 patients without ICA showed pathogenic mutation. Notably, DEPDC5 patients showed ICA in all recorded seizures (n = 15) with apnea duration ranging from 20 seconds to more than 1 minute. All seizures were characterized by motor arrest without overt automatic behaviors during ictal apnea. Scalp EEG showed the involvement of temporal lobe leads in all events. Severe oxygen desaturation was observed in 2 cases. In our cohort, ictal central apnea was a common finding in DEPDC5. These results support (1) the need for respiratory polygraphy during LTVM in DEPDC5-related epilepsy and (2) the potential relevance of genetic testing in patients with focal epilepsy of unknown etiology and ictal apnea.

Multicenter comparative study of polysomnography outcomes in children with the monogenic disorder sickle cell disease.

Sleep-disordered breathing (SDB) is prevalent in children with sickle cell disease (SCD) and is associated with worse outcomes. This study aims to compare the outcomes of polysomnography (PSG) performed for pediatric patients with SCD at three United States centers. We included children with SCD aged 0-21 who underwent PSG at three American Academy of Sleep Medicine accredited centers: the University of Alabama at Birmingham (UAB), the University of Florida (UF), and Duke University Hospital (DUH), between 2012 and 2022. Descriptive statistics were used as appropriate to compare the baseline characters and PSG outcomes among the different centers. A total of 210 children with SCD from the three centers were included, with comparable sex, SCD genotypes, hemoglobin, hematocrit levels, and chronic transfusion. Children from the different centers exhibited variations in age (P < .001), BMI (P < .05), mean corpuscular volume (P < .05), and hydroxyurea use (P < .05) at the time of the PSG. Overall, the three centers showed significantly different PSG outcomes. Patients from UF had worse obstructive sleep apnea, oxygenation, and periodic leg movement events, together with lower hydroxyurea usage. While those from DUH showed higher hypoventilation and arousal indices. This multicenter study underscores variations in PSG outcomes among pediatric SCD patients at different centers in the Southeast United States. These findings emphasize the need for standardized approaches to screen for SDB, refer to PSG, and interpret the results in children with SCD. These conclusions may apply to other genetic disorders associated with an increased risk of sleep-disordered breathing.

Validation of a Textile-Based Wearable Measuring Electrocardiogram and Breathing Frequency for Sleep Apnea Monitoring

Sleep apnea (SA) is a prevalent disorder characterized by recurrent events of nocturnal apnea. Polysomnography (PSG) represents the gold standard for SA diagnosis. This laboratory-based procedure is complex and costly, and less cumbersome wearable devices have been proposed for SA detection and monitoring. A novel textile multi-sensor monitoring belt recording electrocardiogram (ECG) and breathing frequency (BF) measured by thorax excursion was developed and tested in a sleep laboratory for validation purposes. The aim of the current study was to evaluate the diagnostic performance of ECG-derived heart rate variability and BF-derived breathing rate variability and their combination for the detection of sleep apnea in a population of patients with a suspicion of SA. Fifty-one patients with a suspicion of SA were recruited in the sleep laboratory of the Cantonal Hospital St. Gallen. Patients were equipped with the monitoring belt and underwent a single overnight laboratory-based PSG. In addition, some patients further tested the monitoring belt at home. The ECG and BF signals from the belt were compared to PSG signals using the Bland-Altman methodology. Heart rate and breathing rate variability analyses were performed. Features derived from these analyses were used to build a support vector machine (SVM) classifier for the prediction of SA severity. Model performance was assessed using receiver operating characteristics (ROC) curves. Patients included 35 males and 16 females with a median age of 49 years (range: 21 to 65) and a median apnea-hypopnea index (AHI) of 33 (IQR: 16 to 58). Belt-derived data provided ECG and BF signals with a low bias and in good agreement with PSG-derived signals. The combined ECG and BF signals improved the classification accuracy for SA (area under the ROC curve: 0.98; sensitivity and specificity greater than 90%) compared to single parameter classification based on either ECG or BF alone. This novel wearable device combining ECG and BF provided accurate signals in good agreement with the gold standard PSG. Due to its unobtrusive nature, it is potentially interesting for multi-night assessments and home-based patient follow-up.

Detection of Sleep Apnea Using Wearable AI: Systematic Review and Meta-Analysis.

Early detection of sleep apnea, the health condition where airflow either ceases or decreases episodically during sleep, is crucial to initiate timely interventions and avoid complications. Wearable artificial intelligence (AI), the integration of AI algorithms into wearable devices to collect and analyze data to offer various functionalities and insights, can efficiently detect sleep apnea due to its convenience, accessibility, affordability, objectivity, and real-time monitoring capabilities, thereby addressing the limitations of traditional approaches such as polysomnography. The objective of this systematic review was to examine the effectiveness of wearable AI in detecting sleep apnea, its type, and its severity. Our search was conducted in 6 electronic databases. This review included English research articles evaluating wearable AI's performance in identifying sleep apnea, distinguishing its type, and gauging its severity. Two researchers independently conducted study selection, extracted data, and assessed the risk of bias using an adapted Quality Assessment of Studies of Diagnostic Accuracy-Revised tool. We used both narrative and statistical techniques for evidence synthesis. Among 615 studies, 38 (6.2%) met the eligibility criteria for this review. The pooled mean accuracy, sensitivity, and specificity of wearable AI in detecting apnea events in respiration (apnea and nonapnea events) were 0.893, 0.793, and 0.947, respectively. The pooled mean accuracy of wearable AI in differentiating types of apnea events in respiration (normal, obstructive sleep apnea, central sleep apnea, mixed apnea, and hypopnea) was 0.815. The pooled mean accuracy, sensitivity, and specificity of wearable AI in detecting sleep apnea were 0.869, 0.938, and 0.752, respectively. The pooled mean accuracy of wearable AI in identifying the severity level of sleep apnea (normal, mild, moderate, and severe) and estimating the severity score (Apnea-Hypopnea Index) was 0.651 and 0.877, respectively. Subgroup analyses found different moderators of wearable AI performance for different outcomes, such as the type of algorithm, type of data, type of sleep apnea, and placement of wearable devices. Wearable AI shows potential in identifying and classifying sleep apnea, but its current performance is suboptimal for routine clinical use. We recommend concurrent use with traditional assessments until improved evidence supports its reliability. Certified commercial wearables are needed for effectively detecting sleep apnea, predicting its occurrence, and delivering proactive interventions. Researchers should conduct further studies on detecting central sleep apnea, prioritize deep learning algorithms, incorporate self-reported and nonwearable data, evaluate performance across different device placements, and provide detailed findings for effective meta-analyses.

Pharyngeal Manometry and Upper Airway Collapse During Drug-Induced Sleep Endoscopy

Drug-induced sleep endoscopy (DISE) is used to guide therapeutic management of obstructive sleep apnea (OSA), depending on the levels and patterns of pharyngeal collapse. However, the collapsibility of specific pharyngeal sites remains unknown. To assess collapse sites in patients with OSA undergoing DISE and whether number and location are associated with differences in airway collapsibility; and to quantify differences in collapsibility between primary and secondary sites in multilevel collapse. This cohort study assessed adult patients (≥18 years) with OSA undergoing DISE with manometry and positive airway pressure (PAP) titration at a tertiary care center from November 2021 to November 2023. Patients with an AHI score greater than 5 were included; those with less than 1 apnea event during DISE or incorrect catheter placement were excluded. Data were analyzed from September 28, 2022, to March 31, 2024. DISE with manometry and PAP titration. Active pharyngeal critical pressure (Pcrit-A) and pharyngeal opening pressure (PhOP) were used to quantify airway collapsibility, adjusted for covariates (age, sex, race, and body mass index [BMI]). Of 94 screened, 66 patients (mean [SD] age, 57.4 [14.3] years; BMI, 29.2 [3.9]; 51 [77.3%] males) with a mean (SD) apnea-hypopnea index (AHI) of 31.6 (19.0) were included in the analysis. Forty-seven patients (71.2%) had multilevel collapse, 10 (15.2%) had single-level nasopalatal collapse, and 9 (13.6%) had single-level infrapalatal collapse. Groups did not differ in demographic characteristics or established measures of OSA severity. The single-level nasopalatal group had substantially elevated levels of airway collapsibility (Pcrit-A and PhOP covariate adjusted mean, 2.4; 95% CI, 1.1 to 3.8; and 8.2; 95% CI, 6.4 to 9.9 cmH2O) compared to the single-level infrapalatal group (-0.9; 95% CI, -2.4 to 0.5 cmH2O; and 4.9; 95% CI, 3.0 to 6.8 cmH2O, respectively) and similar to the level among the multilevel group (1.3; 95% CI, 0.7 to 2.0; and 8.5; 95% CI, 7.7 to 9.3 cmH2O). The multilevel group had more negative inspiratory pressure (-24.2; 95% CI, -28.1 to -20.2 cmH2O) compared to the single-level nasopalatal group (-9.8; 95% CI, -18.3 to -1.28 cmH2O). In patients with multilevel collapse, airway collapsibility was significantly higher at the primary nasopalatal compared to secondary infrapalatal site (mean difference, 13.7; 95% CI, 11.3 to 16.1 cmH2O). The findings of this cohort study suggest that intervention should target the primary site of pharyngeal collapse, and secondary sites only if they are nearly as collapsible as the primary site. Future work is needed to precisely define the difference in primary and secondary collapsibility that necessitates multilevel treatment.

Indoor air pollution impacts cardiovascular autonomic control during sleep and the inflammatory profile

The present study explores the modifications of cardiovascular autonomic control (CAC) during wake and sleep time and the systemic inflammatory profile associated with exposure to indoor air pollution (IAP) in a cohort of healthy subjects.Twenty healthy volunteers were enrolled. Indoor levels of fine particulate matter (PM2.5), nitrogen dioxide (NO2) and volatile organic compounds (VOCs) were monitored using a portable detector for 7 days. Together, a 7-day monitoring was performed through a wireless patch that continuously recorded electrocardiogram, respiratory activity and actigraphy. Indexes of CAC during wake and sleep time were derived from the biosignals: heart rate and low-frequency to high-frequency ratio (LF/HF), index of sympathovagal balance with higher values corresponding to a predominance of the sympathetic branch. Cyclic variation of heart rate index (CVHRI events/hour) during sleep, a proxy for the evaluation of sleep apnea, was assessed for each night. After the monitoring, blood samples were collected to assess the inflammatory profile. Regression and correlation analyses were performed.A positive association between VOC exposure and the CVHRI (Δ% = +0.2% for 1 μg/m3 VOCs, p = 0.008) was found. The CVHRI was also positively associated with LF/HF during sleep, thus higher CVHRI values corresponded to a shift of the sympathovagal balance towards a sympathetic predominance (r = 0.52; p = 0.018). NO2 exposure was positively associated with both the pro-inflammatory biomarker TREM-1 and the anti-inflammatory biomarker IL-10 (Δ% = +1.2% and Δ% = +2.4%, for 1 μg/m3 NO2; p = 0.005 and p = 0.022, respectively).The study highlights a possible causal relationship between IAP exposure and higher risk of sleep apnea events, associated with impaired CAC during sleep, and a pro-inflammatory state counterbalanced by an increased anti-inflammatory response in healthy subjects. This process may be disrupted in vulnerable populations, leading to a harmful chronic pro-inflammatory profile. Thus, IAP may emerge as a critical and often neglected risk factor for the public health that can be addressed through targeted preventive interventions.

Supine or non-supine sleep apnea events: which can be treated better with Barbed Pharyngoplasty?

Among the treatment options for Obstructive Sleep Apnea (OSA), intrapharyngeal surgery has undergone significant changes and received solid scientific support. However, it is crucial to identify the best candidate. This study aims to present the results of the modified Alianza technique in our clinic to show the differences in the impact of surgery on supine and non-supine apnea levels in moderate-severe OSA patients. Adult patients affected by moderate-severe OSA (Apnea-Hypopnea Index (AHI) > 15), having circular palatal collapse, and candidates for modified Alianza Tecnique were retrospectively enrolled. Each subject performed polysomnography pre- and post-operatively, and the follow-up check was performed after at least six months. This study enrolled 24 patients who underwent the Modified Alianza technique for sleep apnea. We found significant reductions in both supine and non-supine AH) after surgery. Non-supine AHI showed a greater reduction (from 20.89 to 11.64 episodes/hour, p = 0.0001) than supine AHI (from 42.51 to 25.93, p = 0.0003). We subsequently divided the patients into two groups based on whether they were affected by positional OSA before surgery. There was a lower percentage decrease in non-supine AHI compared to supine AHI after surgery in patients who were positional before surgery, but this difference was not statistically significant. Conversely, in the non-positional patient group, there was a higher decrease in non-supine AHI compared to supine AHI, although this was not statistically significant. The Modified Alianza Tecnique leads to notable enhancement in AHI among patients with OSA. Non-supine apneas exhibit a more favorable response to the surgery than supine apneas.

A Systematic Review on Machine Learning / Deep Learning Model-based Detection of Sleep Apnea Using Bio-Signals

Backgrounds: Sleep Apnea (SA) is a sleep-related breathing disorder diagnosed in clinical laboratories. The gold standard is Polysomnography (PSG), a multi-parameter evaluation of a sleep monitoring system that records the biological signals during overnight sleep. Apart from PSG recording, apnea events are recorded by various other bio-signals called Electrocardiogram (ECG), Electroencephalogram (EEG), Oxygen Saturation level (SpO2), etc. Further evaluation of the recorded bio-signals is tedious and time-consuming as experts perform it manually. Aiming to overcome the disadvantage without compromising accuracy, scientists focus on developing robust measurements of SA by using Machine Learning (ML) and Deep Learning (DL) models. Method: This study aimed to analyze the recent research findings in the field of sleep apnea classification and various machine learning and deep learning methods implemented in detecting SA. This study revealed the best-performing technique considering different types of bio-signals used for analysis and the respective ML or DL models used for automatic detection Result: The studies and patents included in this review underwent a precise screening process using PRISMA guidelines. The literature study is comprised of three different analysis tools to showcase the review process and provide evidence for the research findings obtained in the respective publications. The publications considered were limited to the last decade. Conclusion: This review delivers the key finding that ECG signals-based detection of sleep apnea using deep learning model-based deep neural network classifiers will provide more accurate and robust classification, which will pave the way for possible future research directions.

MFS-DBF: A trustworthy multichannel feature sieve and decision boundary formulation system for Obstructive Sleep Apnea detection

The fine identification of sleep apnea events is instrumental in Obstructive Sleep Apnea (OSA) diagnosis. The development of sleep apnea event detection algorithms based on polysomnography is becoming a research hotspot in medical signal processing. In this paper, we propose an Inverse-Projection based Visualization System (IPVS) for sleep apnea event detection algorithms. The IPVS consists of a feature dimensionality reduction module and a feature reconstruction module. First, features of blood oxygen saturation and nasal airflow are extracted and used as input data for event analysis. Then, visual analysis is conducted on the feature distribution for apnea events. Next, dimensionality reduction and reconstruction methods are combined to achieve the dynamic visualization of sleep apnea event feature sets and the visual analysis of classifier decision boundaries. Moreover, the decision-making consistency is explored for various sleep apnea event detection classifiers, which provides researchers and users with an intuitive understanding of the detection algorithm. We applied the IPVS to an OSA detection algorithm with an accuracy of 84% and a diagnostic accuracy of 92% on a publicly available dataset. The experimental results show that the consistency between our visualization results and prior medical knowledge provides strong evidence for the practicality of the proposed system. For clinical practice, the IPVS can guide users to focus on samples with higher uncertainty presented by the OSA detection algorithm, reducing the workload and improving the efficiency of clinical diagnosis, which in turn increases the value of trust.

An audio-semantic multimodal model for automatic obstructive sleep Apnea-Hypopnea Syndrome classification via multi-feature analysis of snoring sounds.

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a common sleep-related breathing disorder that significantly impacts the daily lives of patients. Currently, the diagnosis of OSAHS relies on various physiological signal monitoring devices, requiring a comprehensive Polysomnography (PSG). However, this invasive diagnostic method faces challenges such as data fluctuation and high costs. To address these challenges, we propose a novel data-driven Audio-Semantic Multi-Modal model for OSAHS severity classification (i.e., ASMM-OSA) based on patient snoring sound characteristics. In light of the correlation between the acoustic attributes of a patient's snoring patterns and their episodes of breathing disorders, we utilize the patient's sleep audio recordings as an initial screening modality. We analyze the audio features of snoring sounds during the night for subjects suspected of having OSAHS. Audio features were augmented via PubMedBERT to enrich their diversity and detail and subsequently classified for OSAHS severity using XGBoost based on the number of sleep apnea events. Experimental results using the OSAHS dataset from a collaborative university hospital demonstrate that our ASMM-OSA audio-semantic multimodal model achieves a diagnostic level in automatically identifying sleep apnea events and classifying the four-class severity (normal, mild, moderate, and severe) of OSAHS. Our proposed model promises new perspectives for non-invasive OSAHS diagnosis, potentially reducing costs and enhancing patient quality of life.

Application of multifractal analysis for recognition of sleep apnea using electroencephalogram

Sleep apnea is a common sleep disorder that causes an increased risk of mortality and affects quality of life. Identifying cases of sleep apnea is vital to promptly treating the condition. The goal of the work is to develop a software package for automatically detecting episodes of obstructive sleep apnea syndrome. The paper presents an approach based on the study of multifractal properties of the electroencephalogram (EEG) signal for detecting sleep apnea events. The results of tests conducted using the PhysioNet CAP Sleep database indicate excellent quality of detection of sleep apnea against the background of other diseases: using the Hurst index – sensitivity (90.00%) and specificity (91.50%), using the multifractal detrended fluctuation method analysis (by spectrum width) - sensitivity (90.00%) and specificity (90.50%).The use of a sleep apnea episode recognition system ensures timely detection of the disease at an early stage and thereby improves the effectiveness of the treatment of this disease.

Association of comorbid obstructive sleep apnea and insomnia with risk of major adverse cardiovascular events in sleep medicine center patients

ObjectivesTo investigate the association between comorbid obstructive sleep apnea and insomnia and major adverse cardiovascular events, including myocardial infarction, unstable angina, congestive heart failure, and stroke, in adults with suspected sleep disorders who underwent sleep apnea testing. MethodsWe conducted a retrospective analysis of electronic medical records data from patients with clinical encounters at sleep medicine centers to identify patients with comorbid obstructive sleep apnea and insomnia, obstructive sleep apnea only, insomnia only, and patients without a diagnosis of obstructive sleep apnea or insomnia (i.e., controls). Obstructive sleep apnea, insomnia, comorbidities, and new-onset major adverse cardiovascular events were ascertained by ICD-9-CM and ICD-10-CM codes. Multivariable adjusted Cox proportional regression models evaluated the risk of major adverse cardiovascular events over a 10-year follow-up period. ResultsA total of 3951 patients, 226 controls, 2107 with obstructive sleep apnea only, 276 with insomnia only, and 1342 with comorbid obstructive sleep apnea and insomnia, were included in the analysis. Compared to controls, comorbid obstructive sleep apnea and insomnia were associated with a significantly higher risk of developing major adverse cardiovascular events (hazard ratio 3.60, 95 CI%: 2.33-5.91) in unadjusted analyses. The relationship between comorbid obstructive sleep apnea and insomnia and major adverse cardiovascular events remained after adjustment for demographic and behavioral factors, but not after further adjustment for comorbidities. The greatest risk of major adverse cardiovascular events was found among younger adults with comorbid obstructive sleep apnea and insomnia. Obstructive sleep apnea only was associated with greater risk of major adverse cardiovascular events in unadjusted analyses only (hazard ratio 2.77, 95% CI: 1.80-4.54). Insomnia only was not significantly associated with increased risk of major adverse cardiovascular events. ConclusionsComorbid obstructive sleep apnea and insomnia may be a high-risk group for major adverse cardiovascular events, particularly younger adults. Further research is needed to better understand the association between comorbid obstructive sleep apnea and insomnia and major adverse cardiovascular events risk.

A Case Report of KCNT1 Mutation Presenting as Isolated Apnea and Bradycardia Events (P7-1.006)

A Case Report of KCNT1 Mutation Presenting as Isolated Apnea and Bradycardia Events (P7-1.006)

Apnea, Intermittent Hypoxemia, and Bradycardia Events Predict Late-Onset Sepsis in Infants Born Extremely Preterm

ObjectiveTo examine the association of cardiorespiratory events, including apnea, periodic breathing, intermittent hypoxemia (IH), and bradycardia, with late-onset sepsis for extremely preterm infants (<29 weeks’ gestational age [GA]) on versus off invasive mechanical ventilation. Study designThis is a retrospective analysis of data from infants enrolled in Pre-Vent (ClinicalTrials.gov identifier NCT03174301), an observational study in five level IV neonatal intensive care units. Clinical data were analyzed for 737 infants (mean GA 26.4 weeks, SD 1.71). Monitoring data were available and analyzed for 719 infants (47,512 patient-days), of whom 109 had 123 sepsis events. Using continuous monitoring data, we quantified apnea, periodic breathing, bradycardia, and IH. We analyzed the relationships between these daily measures and late-onset sepsis (positive blood culture >72 hours after birth and ≥5d antibiotics). ResultsFor infants not on a ventilator, apnea, periodic breathing, and bradycardia increased before sepsis diagnosis. During times on a ventilator, increased sepsis risk was associated with longer events with oxygen saturation <80% (IH80) and more bradycardia events before sepsis. IH events were associated with higher sepsis risk, but did not dynamically increase before sepsis, regardless of ventilator status. A multivariable model including post menstrual age, cardiorespiratory variables (apnea, periodic breathing, IH80, and bradycardia), and ventilator status predicted sepsis with an AUC of 0.783. ConclusionWe identified cardiorespiratory signatures of late-onset sepsis. Longer IH events were associated with increased sepsis risk but did not change temporally near diagnosis. Increases in bradycardia, apnea, and periodic breathing preceded the clinical diagnosis of sepsis.

A comparative study in class imbalance mitigation when working with physiological signals.

Class imbalance is a common challenge that is often faced when dealing with classification tasks aiming to detect medical events that are particularly infrequent. Apnoea is an example of such events. This challenge can however be mitigated using class rebalancing algorithms. This work investigated 10 widely used data-level class imbalance mitigation methods aiming towards building a random forest (RF) model that attempts to detect apnoea events from photoplethysmography (PPG) signals acquired from the neck. Those methods are random undersampling (RandUS), random oversampling (RandOS), condensed nearest-neighbors (CNNUS), edited nearest-neighbors (ENNUS), Tomek's links (TomekUS), synthetic minority oversampling technique (SMOTE), Borderline-SMOTE (BLSMOTE), adaptive synthetic oversampling (ADASYN), SMOTE with TomekUS (SMOTETomek) and SMOTE with ENNUS (SMOTEENN). Feature-space transformation using PCA and KernelPCA was also examined as a potential way of providing better representations of the data for the class rebalancing methods to operate. This work showed that RandUS is the best option for improving the sensitivity score (up to 11%). However, it could hinder the overall accuracy due to the reduced amount of training data. On the other hand, augmenting the data with new artificial data points was shown to be a non-trivial task that needs further development, especially in the presence of subject dependencies, as was the case in this work.

Clinical efficacy and mechanism study of mid-frequency anti-snoring device in treating moderate obstructive sleep apnea-hypopnea syndrome.

Obstructive sleep apnea-hypopnea syndrome (OSAHS) is primarily caused by airway obstruction due to narrowing and blockage in the nasal and nasopharyngeal, oropharyngeal, soft palate, and tongue base areas. The mid-frequency anti-snoring device is a new technology based on sublingual nerve stimulation. Its principle is to improve the degree of oropharyngeal airway stenosis in OSAHS patients under mid-frequency wave stimulation. Nevertheless, there is a lack of clinical application and imaging evidence. To investigate the clinical efficacy and mechanisms of a mid-frequency anti-snoring device in treating moderate OSAHS. We selected 50 patients diagnosed with moderate OSAHS in our hospital between July 2022 and August 2023. They underwent a 4-wk treatment regimen involving the mid-frequency anti-snoring device during nighttime sleep. Following the treatment, we monitored and assessed the sleep apnea quality of life index and Epworth Sleepiness Scale scores. Additionally, we performed computed tomography scans of the oropharynx in the awake state, during snoring, and while using the mid-frequency anti-snoring device. Cross-sectional area measurements in different states were taken at the narrowest airway point in the soft palate posterior and retrolingual areas. Compared to pretreatment measurements, patients exhibited a significant reduction in the apnea-hypopnea index, the percentage of time with oxygen saturation below 90%, snoring frequency, and the duration of the most prolonged apnea event. The lowest oxygen saturation showed a notable increase, and both sleep apnea quality of life index and Epworth Sleepiness Scale scores improved. Oropharyngeal computed tomography scans revealed that in OSAHS patients cross-sectional areas of the oropharyngeal airway in the soft palate posterior area and retrolingual area decreased during snoring compared to the awake state. Conversely, during mid-frequency anti-snoring device treatment, these areas increased compared to snoring. The mid-frequency anti-snoring device demonstrates the potential to enhance various sleep parameters in patients with moderate OSAHS, thereby improving their quality of life and reducing daytime sleepiness. These therapeutic effects are attributed to the device's ability to ameliorate the narrowing of the oropharynx in OSAHS patients.

The Prevalence of Sentinel Central Events (SCent) During Drug-Induced Sleep Endoscopy.

With the recent addition of airflow and respiratory effort channels, our group has observed central and mixed apnea events during drug-induced sleep endoscopy (DISE). We measured the frequency and timing of sentinel central and/or mixed events (SCents), as well as assessed for differences in velum, oropharynx, tongue, and epiglottis (VOTE) classification compared to obstructive events. Prospective single-cohort study. Tertiary Care Academic Medical Center. Patients underwent DISE between June 2020 and November 2022. Nasal airflow, thoracoabdominal effort belt signals, and videoendoscopy were simultaneously captured. Demographics, sleep study, and DISE data were compared among patients with and without SCents using Student's T tests or χ2 tests. On average, the cohort (n = 103) was middle-aged (53.5 ± 12.1 years), overweight (body mass index of 29.7 ± 5.3 kg/m2), and had severe obstructive sleep apnea (apnea-hypopnea index of 30.7 ± 18.7 events/h). Forty-seven patients (46%) were found to have at least 1 SCent. Among those with SCent, 45 (95.7%) transitioned to obstructive pathology after an average of 7.91 ± 2.74minutes, with at least 95% of patients expected to do so within 12.57minutes. Twenty-nine out of 47 patients (61.2% [95% confidence interval: 46.4.9%, 75.5%]) with SCent had meaningful differences between central/mixed and obstructive VOTE scores. Central events were present in almost half of our cohort. At least 95% of patients were expected to transition to obstructive events within 12 to 13minutes of propofol initiation. In addition, over half of patients demonstrate significantly different VOTE scores between central and obstructive events. These factors should raise awareness of central events and scoring passive apneas during DISE and consider delaying VOTE scoring.

Influence of Obstructive Apnea Index on Persistent Left Ventricular Dysfunction in Patients with ST-Segment Elevation Myocardial Infarction.

Background: We retrospectively investigated the effects of the severity and classification of sleep-disordered breathing (SDB) on left ventricular (LV) function in patients with ST-segment elevation myocardial infarction (STEMI). Methods: A total of 115 patients with STEMIs underwent a sleep study using a multichannel frontopolar electroencephalography recording device (Sleep Profiler) one week after STEMI onset. We evaluated LV global longitudinal strain (LV-GLS) using two-dimensional echocardiography at one week and seven months. Patients were classified as no SDB (AHI < 5 events/h), obstructive SDB (over 50% of apnea events are obstructive), and central SDB (over 50% of apnea events are central). Due to the device's limitations in distinguishing obstructive from central hypopnea, SDB classification was based on apnea index percentages. Results: The obstructive apnea index (OAI) was significantly associated with LV-GLS at one week (r = 0.24, p = 0.027) and seven months (r = 0.21, p = 0.020). No such correlations were found for the central apnea index and SDB classification. Multivariable regression analysis showed that the OAI was independently associated with LV-GLS at one week (β = 0.24, p = 0.002) and seven months (β = 0.20, p = 0.008). Conclusions: OAI is associated with persistent LV dysfunction assessed by LV-GLS in STEMI.

Real world assessment of reduction of obstructive sleep apnea events by continuous positive airway pressure using a continuous large U.S. sample by home under-mattress devices

Real world assessment of reduction of obstructive sleep apnea events by continuous positive airway pressure using a continuous large U.S. sample by home under-mattress devices